0
| 本文作者： 奕欣 | 2017-08-24 09:14 | 專題：KDD 2017 |
KDD 2017 已于近日落下帷幕，作為數(shù)據(jù)科學、信息檢索、數(shù)據(jù)挖掘和機器學習的頂級會議，KDD 為學術(shù)界和工業(yè)界提供了一個寶貴的交流機會。
一直以來，谷歌都是 KDD 的積極參與者，自然，今年的 KDD 也不例外，一起和雷鋒網(wǎng) AI 科技評論來看看谷歌是如何深度參與 KDD 的吧。
以下是谷歌深度參與或介入的 KDD 活動議程全名單，雷鋒網(wǎng)AI科技評論編譯如下：
Panel 主席: Andrew Tomkins
研究程序委員會主席: Ravi Kumar
應用數(shù)據(jù)科學程序委員會主席: Roberto J. Bayardo
研究程序委員會: Sergei Vassilvitskii, Alex Beutel, Abhimanyu Das, Nan Du, Alessandro Epasto, Alex Fabrikant, Silvio Lattanzi, Kristen Lefevre, Bryan Perozzi, Karthik Raman, Steffen Rendle, Xiao Yu
應用數(shù)據(jù)科學程序委員會: Edith Cohen, Ariel Fuxman, D. Sculley, Isabelle Stanton, Martin Zinkevich, Amr Ahmed, Azin Ashkan, Michael Bendersky, James Cook, Nan Du, Balaji Gopalan, Samuel Huston, Konstantinos Kollias, James Kunz, Liang Tang, Morteza Zadimoghaddam
Bryan Perozzi
論文名稱：Local Modeling of Attributed Graphs: Algorithms and Applications
論文地址：http://perozzi.net/publications/16_thesis.pdf
SIGKDD 2017 的博士論文獎被谷歌的 Bryan Perozzi 摘得，這一獎項被授予在數(shù)據(jù)挖掘和知識發(fā)現(xiàn)領(lǐng)域有所建樹的杰出博士生。
這一獎項是為了肯定他在石溪大學跟隨 Steven Skiena 教授所做的圖表機器學習研究課題《Local Modeling of Attributed Graphs: Algorithms and Applications》，其中的一部分內(nèi)容是 Perozzi 在 Google 實習期間完成的。
這一研究課題使用局限圖原語（例如 ego－network 和截取的隨機散列）有效地利用每個頂點周圍的信息進行分類、聚類和異常檢測。值得一提的是，這項工作在 DeepWalk 中采用了神經(jīng)網(wǎng)絡(luò)圖形嵌入的隨機游走范式。
《DeepWalk: Online Learning of Social Representations》實際上是 Bryan Perozzi 最初在 KDD』14 投遞的一篇論文，論文使用從截斷的隨機游走獲得的一系列本地信息，以學習圖中節(jié)點的潛在表征（如社交網(wǎng)絡(luò)用戶）的方法。其核心思想是將隨機游走的每一段都視為「圖形語言中」（ 「in the language of the graph」 ）的句子，然后可以使用這些片段作為神經(jīng)網(wǎng)絡(luò)模型的輸入來學習圖形節(jié)點的表征。這項研究將繼續(xù)在谷歌進行，比如最近的 Learning Edge Representations via Low-Rank Asymmetric Projections。
Alex Beutel
論文名稱：User Behavior Modeling with Large-Scale Graph Analysis
論文地址：http://alexbeutel.com/papers/CMU-CS-16-105.pdf
（斜體為非谷歌員工）
Ego-Splitting Framework: from Non-Overlapping to Overlapping Clusters
Alessandro Epasto, Silvio Lattanzi, Renato Paes Leme
HyperLogLog Hyperextended: Sketches for Concave Sublinear Frequency Statistics
Edith Cohen
Google Vizier: A Service for Black-Box Optimization
Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, D. Sculley
論文地址：http://dl.acm.org/citation.cfm?id=3098043
Quick Access: Building a Smart Experience for Google Drive
Sandeep Tata, Alexandrin Popescul, Marc Najork, Mike Colagrosso, Julian Gibbons, Alan Green, Alexandre Mah, Michael Smith, Divanshu Garg, Cayden Meyer, Reuben KanPapers
論文地址：http://www.kdd.org/kdd2017/papers/view/quick-access-building-a-smart-experience-for-google-drive
TFX: A TensorFlow- Based Production -Scale Machine Learning Platform
Denis Baylor, Eric Breck, Heng-Tze Cheng, Noah Fiedel, Chuan Yu Foo, Zakaria Haque, Salem Haykal, Mustafa Ispir, Vihan Jain, Levent Koc, Chiu Yuen Koo, Lukasz Lew, Clemens Mewald, Akshay Modi, Neoklis Polyzotis, Sukriti Ramesh, Sudip Roy, Steven Whang, Martin Wicke, Jarek Wilkiewicz, Xin Zhang, Martin Zinkevich
Construction of Directed 2K Graphs
Balint Tillman, Athina Markopoulou, Carter T. Butts, Minas Gjoka
論文地址：http://www.kdd.org/kdd2017/papers/view/construction-of-directed-2k-graphs
A Practical Algorithm for Solving the Incoherence Problem of Topic Models In Industrial Applications
Amr Ahmed, James Long, Dan Silva, Yuan Wang
Train and Distribute: Managing Simplicity vs. Flexibility in High--Level Machine Learning Frameworks
Heng-Tze Cheng, Lichan Hong, Mustafa Ispir, Clemens Mewald, Zakaria Haque, Illia Polosukhin, Georgios Roumpos, D Sculley, Jamie Smith, David Soergel, Yuan Tang, Philip Tucker, Martin Wicke, Cassandra Xia, Jianwei Xie
Learning to Count Mosquitoes for the Sterile Insect Technique
Yaniv Ovadia, Yoni Halpern, Dilip Krishnan, Josh Livni, Daniel Newburger, Ryan Poplin, Tiantian Zha, D. Sculley
論文地址：http://www.kdd.org/kdd2017/papers/view/learning-to-count-mosquitoes-for-the-sterile-insect-technique
13th International Workshop on Mining and Learning with Graphs
受邀講者：Vahab Mirrokni - Distributed Graph Mining: Theory and Practice
contributed talks：
HARP: Hierarchical Representation Learning for Networks
Haochen Chen, Bryan Perozzi, Yifan Hu and Steven Skiena
Fairness, Accountability, and Transparency in Machine Learning
Contributed talks：
Fair Clustering Through Fairlets
Flavio Chierichetti, Ravi Kumar, Silvio Lattanzi, Sergei Vassilvitskii
Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
Alex Beutel, Jilin Chen, Zhe Zhao, Ed H. Chi
TensorFlow
Rajat Monga, Martin Wicke, Daniel ‘Wolff’ Dobson, Joshua Gordon
更多精彩內(nèi)容敬請關(guān)注雷鋒網(wǎng)AI科技評論。
專題
